Built-in bionic smell recognition method and device

An identification method and embedded technology, applied in instruments, complex mathematical operations, material resistance, etc., can solve the problems of ineffective detection, difficult operation, complicated equipment, etc., and achieve the effect of convenient operation, strong versatility and small size

Inactive Publication Date: 2009-07-01
GUANGDONG UNIV OF TECH +1
View PDF0 Cites 57 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the complex equipment used in gas chromatography analysis, the operation is difficult and the accuracy is low, it is difficult to achieve online or on-site detection and analysis; in addition, because the smell and taste of food are not formed by a single component, but a comprehensive reflection o

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Built-in bionic smell recognition method and device
  • Built-in bionic smell recognition method and device
  • Built-in bionic smell recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] Technical scheme of the present invention is:

[0032] Embedded bionic olfactory smell recognition method of the present invention, it comprises the following steps:

[0033] 1) Use the array sensor to test as many known odors as possible, and obtain the response patterns to various odors, so as to establish an information database of known odors;

[0034] 2) Pre-processing the odor information detected by the sensor array to achieve drift compensation, information compression and noise filtering;

[0035] 3) Post-processing the pre-processed odor information, extracting the characteristics of the odor information to be tested, reducing the measurement space dimension and extracting information related to pattern recognition;

[0036] 4) Carry out characteristic classification of the odor information of the odor to be identified;

[0037] 5) Compare the obtained characteristic classification of the odor to be recognized with the known odor characteristic information i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an embedded bionic olfaction smell recognition method and a device, for simulating the olfactory function of humans/animals, recognizing and analyzing the volatile gas having mixed multiple components. The embedded bionic olfaction smell recognition method comprises: (1) using an array sensor to test known smells as much as possible, to obtain a response mode for each smell, thereby establishing an information database of known smells; (2) processing pretreatment on the object smell information detected by the sensor array to realize drift compensation, information compression and noise filter; (3) processing post treatment on the smell information after pretreatment, to extract the characteristics of the object smell information, reduce measurement spatial dimension and extract the information relative to mode recognition; (4) classifying the smell information of the object smell via characteristics; (5) comparing the obtained characteristic classes of the object smell with the known smell characteristic information in the database to provide a recognition result. The invention can recognize different smells, to resolve the selectivity problem of prior single gas sensor. The analyzing device has wide smell map sensitive recognition range.

Description

Technical field: [0001] The invention is an embedded bionic olfactory smell recognition method and device that imitates the olfactory function of humans / animals and can identify and analyze multi-component mixed volatile gases, and belongs to the innovative technology of the embedded bionic olfactory smell recognition method and device. Background technique: [0002] With the in-depth study of bionics theory and the development of computer technology, people began to study bionic olfactory and taste systems in the 1980s. Especially in recent years, with the development of material science and the development of electronic information technology, the development of international electronic nose has achieved rapid development and entered the practical stage. [0003] At present, the final appraisal of food quality and aroma quality by most domestic food companies mainly depends on the human body's sense of taste and smell. Since human senses are inevitably affected by subject...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G01N35/00G01N27/04G06F17/10
Inventor 骆德汉汪军邹宇华
Owner GUANGDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products